Skip to main content

2020 | OriginalPaper | Buchkapitel

Unsupervised Learning of Spatio-Temporal Receptive Fields from an Event-Based Vision Sensor

verfasst von : Thomas Barbier, Céline Teulière, Jochen Triesch

Erschienen in: Artificial Neural Networks and Machine Learning – ICANN 2020

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Neuromorphic vision sensors exhibit several advantages compared to conventional frame-based cameras including low latencies, high dynamic range, and low data rates. However, how efficient visual representations can be learned from the output of such sensors in an unsupervised fashion is still an open problem. Here we present a spiking neural network that learns spatio-temporal receptive fields in an unsupervised way from the output of a neuromorphic event-based vision sensor. Learning relies on the combination of spike timing-dependent plasticity with different synaptic delays, the homeostatic regulations of synaptic weights and firing thresholds, and fast inhibition among neurons to decorrelate their responses. Our network develops biologically plausible spatio-temporal receptive fields when trained on real world input and is suited for implementation on neuromorphic hardware.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Akolkar, H., Panzeri, S., Bartolozzi, C.: Spike time based unsupervised learning of receptive fields for event-driven vision. In: IEEE International Conference on Robotics and Automation. IEEE, May 2015 Akolkar, H., Panzeri, S., Bartolozzi, C.: Spike time based unsupervised learning of receptive fields for event-driven vision. In: IEEE International Conference on Robotics and Automation. IEEE, May 2015
3.
Zurück zum Zitat Borst, A.: Models of motion detection. Nat. Neurosci. 3(1), 1168 (2000)CrossRef Borst, A.: Models of motion detection. Nat. Neurosci. 3(1), 1168 (2000)CrossRef
4.
Zurück zum Zitat Brandli, C., Berner, R., Yang, M., Liu, S.C., Delbruck, T.: A 240 \(\times \) 180 130 dB 3 \(\mu \)s latency global shutter spatiotemporal vision sensor. IEEE J. Solid-State Circuits 49(10), 2333–2341 (2014) Brandli, C., Berner, R., Yang, M., Liu, S.C., Delbruck, T.: A 240 \(\times \) 180 130 dB 3 \(\mu \)s latency global shutter spatiotemporal vision sensor. IEEE J. Solid-State Circuits 49(10), 2333–2341 (2014)
5.
Zurück zum Zitat Diehl, P.U., Cook, M.: Unsupervised learning of digit recognition using spike-timing-dependent plasticity. Front. Comput. Neurosci. 9 (2015) Diehl, P.U., Cook, M.: Unsupervised learning of digit recognition using spike-timing-dependent plasticity. Front. Comput. Neurosci. 9 (2015)
6.
Zurück zum Zitat Haessig, G., Cassidy, A., Alvarez, R., Benosman, R., Orchard, G.: Spiking optical flow for event-based sensors using IBM’s TrueNorth neurosynaptic system. IEEE Trans. Biomed. Circuits Syst. 12(4), 860–870 (2018)CrossRef Haessig, G., Cassidy, A., Alvarez, R., Benosman, R., Orchard, G.: Spiking optical flow for event-based sensors using IBM’s TrueNorth neurosynaptic system. IEEE Trans. Biomed. Circuits Syst. 12(4), 860–870 (2018)CrossRef
7.
Zurück zum Zitat Hopkins, M., Pineda-García, G., Bogdan, P.A., Furber, S.B.: Spiking neural networks for computer vision. Interface Focus. 8(4), 20180007 (2018)CrossRef Hopkins, M., Pineda-García, G., Bogdan, P.A., Furber, S.B.: Spiking neural networks for computer vision. Interface Focus. 8(4), 20180007 (2018)CrossRef
8.
Zurück zum Zitat Kheradpisheh, S.R., Ganjtabesh, M., Thorpe, S.J., Masquelier, T.: STDP-based spiking deep convolutional neural networks for object recognition. Neural Netw. 99, 56–67 (2018)CrossRef Kheradpisheh, S.R., Ganjtabesh, M., Thorpe, S.J., Masquelier, T.: STDP-based spiking deep convolutional neural networks for object recognition. Neural Netw. 99, 56–67 (2018)CrossRef
9.
Zurück zum Zitat Li, B., Peterson, M.R., Freeman, R.D.: Oblique effect: a neural basis in the visual cortex. J. Neurophysiol. 90(1), 204–217 (2003)CrossRef Li, B., Peterson, M.R., Freeman, R.D.: Oblique effect: a neural basis in the visual cortex. J. Neurophysiol. 90(1), 204–217 (2003)CrossRef
10.
Zurück zum Zitat Orchard, G., Benosman, R., Etienne-Cummings, R., Thakor, N.V.: A spiking neural network architecture for visual motion estimation. In: IEEE Biomedical Circuits and Systems Conference (BioCAS), October 2013 Orchard, G., Benosman, R., Etienne-Cummings, R., Thakor, N.V.: A spiking neural network architecture for visual motion estimation. In: IEEE Biomedical Circuits and Systems Conference (BioCAS), October 2013
11.
Zurück zum Zitat Paredes-Valles, F., Scheper, K.Y.W., Croon, G.C.H.E.D.: Unsupervised learning of a hierarchical spiking neural network for optical flow estimation: from events to global motion perception. IEEE Trans. Pattern Anal. Mach. Intell. 42, 2051–2064 (2018) Paredes-Valles, F., Scheper, K.Y.W., Croon, G.C.H.E.D.: Unsupervised learning of a hierarchical spiking neural network for optical flow estimation: from events to global motion perception. IEEE Trans. Pattern Anal. Mach. Intell. 42, 2051–2064 (2018)
12.
Zurück zum Zitat Paulun, L., Wendt, A., Kasabov, N.: A retinotopic spiking neural network system for accurate recognition of moving objects using NeuCube and dynamic vision sensors. Front. Comput. Neurosci. 12, 13 Pages (2018). Article no: 42 Paulun, L., Wendt, A., Kasabov, N.: A retinotopic spiking neural network system for accurate recognition of moving objects using NeuCube and dynamic vision sensors. Front. Comput. Neurosci. 12, 13 Pages (2018). Article no: 42
13.
Zurück zum Zitat Perez-Carrasco, J.A., Serrano, C., Acha, B., Serrano-Gotarredona, T., Linares-Barranco, B.: Spike-based convolutional network for real-time processing. In: IAPR International Conference on Pattern Recognition. IEEE, August 2010 Perez-Carrasco, J.A., Serrano, C., Acha, B., Serrano-Gotarredona, T., Linares-Barranco, B.: Spike-based convolutional network for real-time processing. In: IAPR International Conference on Pattern Recognition. IEEE, August 2010
14.
Zurück zum Zitat Rebecq, H., Gehrig, D., Scaramuzza, D.: ESIM: an open event camera simulator. In: Conference on Robot Learning, October 2018 Rebecq, H., Gehrig, D., Scaramuzza, D.: ESIM: an open event camera simulator. In: Conference on Robot Learning, October 2018
15.
Zurück zum Zitat Rothkopf, C.A., Weisswange, T.H., Triesch, J.: Learning independent causes in natural images explains the spacevariant oblique effect. ICDL 2009. IEEE 8th International Conference on Development and Learning, pp. 1–6, January 2009 Rothkopf, C.A., Weisswange, T.H., Triesch, J.: Learning independent causes in natural images explains the spacevariant oblique effect. ICDL 2009. IEEE 8th International Conference on Development and Learning, pp. 1–6, January 2009
16.
Zurück zum Zitat Stromatias, E., Soto, M., Serrano-Gotarredona, T., Linares-Barranco, B.: An event-driven classifier for spiking neural networks fed with synthetic or dynamic vision sensor data. Front. Neurosci. 11, 17 Pages (2017). Article no: 350 Stromatias, E., Soto, M., Serrano-Gotarredona, T., Linares-Barranco, B.: An event-driven classifier for spiking neural networks fed with synthetic or dynamic vision sensor data. Front. Neurosci. 11, 17 Pages (2017). Article no: 350
17.
Zurück zum Zitat Tien, N.W., Kerschensteiner, D.: Homeostatic plasticity in neural development. Neural Dev.13(1), 7 Pages (2018) Tien, N.W., Kerschensteiner, D.: Homeostatic plasticity in neural development. Neural Dev.13(1), 7 Pages (2018)
18.
Zurück zum Zitat Triesch, J., Vo, A.D., Hafner, A.S.: Competition for synaptic building blocks shapes synaptic plasticity. Elife 7, e37836 (2018)CrossRef Triesch, J., Vo, A.D., Hafner, A.S.: Competition for synaptic building blocks shapes synaptic plasticity. Elife 7, e37836 (2018)CrossRef
20.
Zurück zum Zitat Zhao, B., Ding, R., Chen, S., Linares-Barranco, B., Tang, H.: Feedforward categorization on AER motion events using cortex-like features in a spiking neural network. IEEE Trans. Neural Netw. Learn. Syst. 26(9), 1963–1978 (2015)MathSciNetCrossRef Zhao, B., Ding, R., Chen, S., Linares-Barranco, B., Tang, H.: Feedforward categorization on AER motion events using cortex-like features in a spiking neural network. IEEE Trans. Neural Netw. Learn. Syst. 26(9), 1963–1978 (2015)MathSciNetCrossRef
Metadaten
Titel
Unsupervised Learning of Spatio-Temporal Receptive Fields from an Event-Based Vision Sensor
verfasst von
Thomas Barbier
Céline Teulière
Jochen Triesch
Copyright-Jahr
2020
DOI
https://doi.org/10.1007/978-3-030-61616-8_50